© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7098
    Prev
    Next
    INDEX
    Explanations

    a variety of numerical values, symbols and units, sometimes interspersed within text

    oai_token-act-pair · gemini-2.0-flash

    numbers in the twenties/thirties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     four
    -1.20
     three
    -1.20
     quatre
    -1.10
     trois
    -1.07
    three
    -1.07
    Three
    -1.06
     Three
    -1.01
     quatro
    -0.98
     Four
    -0.96
     five
    -0.95
    POSITIVE LOGITS
     Thirty
    1.13
     Twenty
    1.08
    Twenty
    1.05
     thirty
    1.02
     twenty
    0.99
    Thirty
    0.98
     Seventeen
    0.96
    twenty
    0.96
     TWENTY
    0.94
     Seventeenth
    0.88
    Activations Density 2.430%

    No Known Activations